VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrievalby…
Thai Financial Domain Adaptation of THaLLE – Technical Reportby KBTG Labs, Atthakorn Petchsod, Pornchanan Balee,…
When Babies Teach Babies: Can student knowledge sharing outperform Teacher-Guided Distillation on small datasets?by Srikrishna…
ENCLIP: Ensembling and Clustering-Based Contrastive Language-Image Pretraining for Fashion Multimodal Search with Limited Data and…
CLIP Unreasonable Potential in Single-Shot Face Recognitionby Nhan T. LuuFirst submitted to arxiv on: 19…
On the Shortcut Learning in Multilingual Neural Machine Translationby Wenxuan Wang, Wenxiang Jiao, Jen-tse Huang,…
Training Data for Large Language Modelby Yiming Ju, Huanhuan MaFirst submitted to arxiv on: 12…
Zyda-2: a 5 Trillion Token High-Quality Datasetby Yury Tokpanov, Paolo Glorioso, Quentin Anthony, Beren MillidgeFirst…
MetaSSC: Enhancing 3D Semantic Scene Completion for Autonomous Driving through Meta-Learning and Long-sequence Modelingby Yansong…
Visual Fourier Prompt Tuningby Runjia Zeng, Cheng Han, Qifan Wang, Chunshu Wu, Tong Geng, Lifu…